Altmetric has launched a new Beta feature, Sentiment Analysis, which uses AI and a Large Language Model to interpret the opinions expressed in online mentions of research outputs. 

Initially focusing on posts from X (formerly Twitter) and Bluesky, the tool assigns sentiment scores from -3 (strongly negative) to 3 (strongly positive), indicating whether posts express positive, negative, or neutral opinions about research. This feature, displayed in Altmetric Explorer and on Details Pages, provides context beyond mere mention counts, helping users understand research reception, impact, and potential risks. 

Displayed in Altmetric Explorer and Details Pages, sentiment data adds valuable context to engagement metrics by revealing how research is perceived.

More information on sentiment analysis, score definitions, and usage can be found here.